Name: 如何讓 NotebookLM 比 99% 的人更好用！ (How to Use Notebooklm Better than 99% of People)
Uploaded: 2025-12-27T05:01:28.000Z
Duration: 19 min 7 s

Right now, the Average user treats NoteBookLM like the usual basic chatbot.

現在，一般使用者把 NoteBookLM 當成一般的 chatbot 使用。

They upload a file or two, ask a question, and maybe click around hoping to find something useful.

他們上傳一兩個檔案，問個問題，然後可能隨便點擊，希望能找到點什麼。

But that is a massive underutilization of the tool.

但這完全是浪費了這個工具的潛力。

因為 NoteBookLM 不只是一個 chatbot。

It is a complete research intelligence system.

它是一個完整的研究情報系統。

We are talking about autonomous sourcing that finds data for you, validation methods that ensure your research is reliable, and

我們講的是自動化採集，能幫你找到資料，還有驗證方法，確保你的研究可靠，

even generative workflows that turn that data into slide decks and infographics instantly.

甚至是生成式工作流程，能立刻將資料轉化成簡報和圖表。

So in this video, I'm going to walk you through the complete advanced workflow to get you using this tool better than 99% of people.

所以在這個影片裡，我會帶你走過完整的進階工作流程，讓你比 99% 的人更懂得使用這個工具。

And by the end of this, you'll know exactly how to use NotebookLM the way it is actually meant to be used.

影片結束後，你就會確切知道如何使用 NoteBookLM，讓它發揮真正的價值。

First, I'll head over to the NotebookLM website and on the homepage you'll see your notebook list if you've created any before, or an empty state if this is your first time.

首先，我會連到 NoteBookLM 的網站，在首頁你會看到你的筆記本列表（如果你之前有建立過的話），或是空白狀態（如果你是第一次使用）。

所以我們可以在這裡建立一個新的筆記本。

But before we do, here is a critical detail that often gets overlooked.

但在我們開始之前，這裡有個很重要的細節，常常會被忽略。

It's that notebooks should be topic specific.

那就是筆記本應該要是特定主題的。

Don't create a notebook called Research or General Notes.

不要建立一個叫做「研究」或「一般筆記」的筆記本。

Create focused notebooks like competitive analysis, Q1, 2025 or AI video generation research.

請建立像「市場競爭分析」、「2025年第一季度」或「AI影片生成研究」這種專注的筆記本。

But it actually matters because NotebookLM performs better when sources are related and focused on a single topic or project.

但這其實很重要，因為當來源是相關且專注於單一主題或專案時，NoteBookLM 的表現會更好。

I'll go ahead and create a new notebook here by pressing this plus icon and this immediately takes you to the source upload screen.

我會點擊這個加號圖示來建立一個新的筆記本，這會立刻帶你到來源上傳畫面。

This is where the quality of your output gets decided.

在這裡，你的輸出品質就決定了。

The common mistake here is simply uploading one or two files without thinking strategically about what sources you actually need.

大家常犯的錯誤是隨便上傳一兩個檔案，卻沒有策略性地思考自己真正需要的來源。

Think about the complete information landscape for your topic.

想想看你主題的完整資訊圖像。

What formats does your information exist in?

PDFs, YouTube videos, websites, Google Docs?

PDF、YouTube 影片、網站、Google 文件？

The power of NotebookLM comes from combining multiple formats and sources, creating a web of information rather than just a stack of isolated documents.

NoteBookLM 的強大之處在於結合多種格式和來源，建立一個資訊網絡，而不是一堆孤立的文件。

And later in this video I will show you exactly how to professionally execute that multi format strategy.

稍後在這支影片中，我會確切地示範如何專業地執行這種多格式策略。

For this example, I'm going to create a research notebook on AI alignment.

在這個範例中，我將建立一個關於 AI 對齊的研究筆記本。

Let's hit Escape and I'll go right up here and title this AI Alignment Research.

我們按 Escape 鍵，然後到這裡為這個筆記本命名為「AI Alignment Research」。

Now here's a feature that was added quite recently which is the Deep Research Source Discovery.

現在有一個最近才加入的功能，叫做「深度研究來源發現」。

Previously there was only fast research which was good but limited.

以前只有快速研究，雖然不錯但有限。

But now you can access a much more powerful agent by clicking this drop down arrow and selecting Deep Research.

但現在你可以透過點擊這個下拉箭頭並選擇「深度研究」，來存取一個更強大的代理工具。

So I'M going to select that and write AI Alignment and safety challenges Hit submit and here's what happens.

所以我將選擇它，然後輸入「AI 對齊與安全挑戰」，按下提交，看看會發生什麼。

NotebookLM launches an agentic AI tool that autonomously researches your topic.

NoteBookLM 會啟動一個代理式 AI 工具，自動化地研究你的主題。

It doesn't just do keyword matching like a basic search, it actually analyzes the topic, finds sources, evaluates them, adapts its search strategy to fill gaps, and

它不像基本搜尋那樣只做關鍵字比對，它會實際分析主題、尋找來源、評估它們、調整搜尋策略來填補空白，並且

generates a comprehensive research report, which means Deep Research will be able to discover around 50 sources related to your topic.

生成一份全面的研究報告，這表示「深度研究」將能發現大約 50 個與你主題相關的來源。

It generates a detailed research report synthesizing those sources.

它會生成一份詳細的研究報告，綜合這些來源。

Then it selects the most relevant sources and imports them directly into your notebook.

然後它會挑選最相關的來源，並直接匯入你的筆記本。

What you get is both a curated research report and high quality sources already loaded and ready to work with.

你將獲得一份精選的研究報告，以及已經載入、準備好使用的優質來源。

And that matters a lot because most people spend hours manually searching for sources, evaluating quality and uploading them one by one.

這點非常重要，因為大部分人都要花好幾個小時手動搜尋來源、評估品質，然後一個一個匯入。

Deep Research does that work in minutes, and often finds sources you wouldn't have discovered manually.

Deep Research 幾分鐘內就能完成這些工作，而且常常能找到你手動搜尋時發現不了的來源。

I now have a curated list of citations imported automatically, plus a full research report that's also added as a source.

我現在有一份自動匯入的精選引用列表，還有一份完整的研究報告，這份報告也一併被加入為來源。

Scrolling down, you'll notice some sources might fail to import if they're behind paywalls.

往下滑，你會發現有些來源如果設在付費牆後面，可能會匯入失敗。

There's a Remove all failed sources button that cleans those up in one click instead of deleting them individually, which I'm going to do right now.

有一個「移除所有失敗的來源」按鈕，可以一次性清除這些來源，而不是一個一個刪除，我現在就來操作一下。

Now I have a strong foundation of sources to work with before we start asking questions or generating content.

現在我有了紮實的來源基礎，可以開始提問或生成內容了。

Here's a step that gets skipped 9 times out of 10, which is source validation.

這是 10 次中有 9 次會被跳過的步驟，也就是來源驗證。

NotebookLM is extremely good at reducing hallucinations because it grounds everything in your sources, but

NotebookLM 在減少幻覺方面非常厲害，因為它會將所有內容都建立在你提供的來源上，但是

that only works if your sources are reliable and current.

這只有在你的來源可靠且是最新資料時才有效。

If your sources are outdated, biased toward one perspective, or mixing PR primary research with opinion pieces, NotebookLM will give you answers based on flawed information without distinguishing between them.

如果你的來源過時、有偏見，或是將公關文案、一手研究和評論文章混在一起，NotebookLM 就會根據有問題的資訊給你答案，而且不會區分它們。

So here is the validation framework I use for every single notebook.

所以，這是我為每個筆記本使用的驗證框架。

Go to the chat interface in the center of the screen.

Before asking any topic questions, I run through these checks.

在問任何主題問題之前，我都會執行這些檢查。

First I ask Create a table showing each source with its publication date, author credentials, and

首先，我要求建立一個表格，顯示每個來源及其出版日期、作者資格，

whether it's a primary source, secondary analysis, or opinion piece.

以及它是一手來源、二手分析還是評論文章。

This gives me a clear view of what I'm actually working with.

這樣我就可以清楚地知道我實際在處理什麼。

If I see that most of my sources are from 2020 or earlier on a fast moving topic like AI, I know I need newer material.

如果我發現大多數來源都是 2020 年或更早的，而主題像 AI 這種變化快速的，我就知道我需要更新的資料。

If everything is opinion pieces with no primary research, that's a problem.

如果所有內容都是評論文章，沒有一手研究，那就麻煩了。

Now Notebook LM is generating a table analyzing all of the sources.

現在 NoteBookLM 正在生成一個分析所有來源的表格。

I can immediately see the spread when these were published, who wrote them, and

我能立刻看到這些資料的發布時間、作者是誰，以及

In this case, I'm seeing a good mix of recent academic papers, industry reports, and technical documentation.

在這個例子中，我看到近期學術論文、產業報告和技術文件都有不錯的組合。

Most of them are pretty recent, which is what I want for current AI alignment research.

大部分都相當新，這正是我想要的，用於目前的 AI 對齊研究。

Second, I ask which of these sources are most frequently cited or referenced by other sources in this notebook.

第二，我會問，在這些來源中，哪些在筆記本裡被其他來源引用或參考的頻率最高。

This shows me which sources are foundational to the topic versus which ones are peripheral.

這能讓我瞭解哪些來源是這個主題的基礎，哪些是比較邊緣的。

The highly cited sources are usually the ones I should prioritize when I'm filtering sources later.

被高度引用的來源通常是我之後篩選來源時應該優先考慮的。

And third, I ask summarize the primary perspective or bias of the top five most substantial sources.

第三，我會要求總結排名前五個最有份量的來源的主要觀點或偏見。

This tells me whether I'm looking at this topic from multiple angles or whether all my sources share the same viewpoint.

這能告訴我，我是從多個角度看待這個主題，還是我所有的來源都持有相同的觀點。

For controversial or evolving topics, you want diverse perspectives.

對於有爭議或正在發展的主題，你需要多元的觀點。

For technical documentation, perspective matters less.

對於技術文件，觀點就沒那麼重要了。

These three checks take about five minutes total, but

這三個檢查總共大概只需要五分鐘，

they give me a complete picture of my source quality before I build my entire workflow on top of it.

但它們能讓我在建構整個工作流程之前，對我的來源品質有全面的瞭解。

With our sources validated, the next critical step is configuration.

在驗證了我們的來源之後，下一個關鍵步驟就是設定。

This is something the vast majority of users ignore, but it dramatically improves response quality.

這是絕大多數使用者都會忽略的一點，但它能大幅提升回應的品質。

In the top right corner, click right here.

This opens settings that control how NotebookLM responds to you.

這會打開控制 NotebookLM 如何回應你的設定。

You have three default for general research, learning Guide for educational content, or Custom for specific use cases.

你有三個預設選項：一般研究、學習指南（用於教育內容），或自訂（用於特定用途）。

For this research notebook, I'm choosing Custom and I'll define the role as research Analyst focused on AI safety and alignment debates.

針對這個研究筆記本，我會選擇「自訂」，並將角色設定為專注於 AI 安全與對齊辯論的研究分析師。

This tells NotebookLM to frame all responses from that perspective instead of giving generic answers.

這會讓 NotebookLM 從這個角度來回應，而不是給出一般性的答案。

你有預設的「較長」或「較短」。

For research work, I typically choose longer because I want detailed analysis, not brief summaries.

對於研究工作，我通常會選擇「較長」，因為我想要詳細的分析，而不是簡短的摘要。

These settings now apply to every chat in this notebook.

這些設定現在會套用到此筆記本中的每一個對話。

You set them once and forget about them, but they shape every interaction from this point forward.

你設定一次後就可以不用管它，但它們會塑造之後的每一次互動。

The majority of the people use notebooks in default mode and wonder why responses feel generic.

絕大多數人都是用預設模式來使用筆記本，然後納悶為什麼回應感覺很普通。

Configured settings give you targeted role specific answers optimized for your exact use case.

設定好的參數會給你針對性的、符合你確切使用情境的特定角色回應。

Now let's look at how to work with sources strategically instead of just accepting all of the sources for every query.

現在我們來看看如何策略性地處理來源，而不是每次查詢都接受所有來源。

On the left side you'll see your source list with these checkboxes next to each file and A very common mistake that people make is that they leave everything checked all the time.

左邊你會看到來源列表，每個檔案旁邊都有核取方塊，一個很常見的錯誤是大家總是讓所有項目都保持勾選狀態。

When you ask a question with all of the sources selected, NotebookLM tries to synthesize an answer from every single document.

當你勾選所有來源來提問時，NoteBookLM 會試圖從每一份文件中綜合出一個答案。

It forces the AI to generalize, giving you a vague surface level summary instead of a deep answer.

它會迫使 AI 泛化，給你一個籠統的表面總結，而不是深入的答案。

So let's say I want to focus specifically on existential risk.

所以，假設我想專注於生存風險。

If I leave the mechanistic interpretability checked, I am confusing the model by forc it to look at conflicting topics.

如果我勾選了「機制可解釋性」，我就會強迫它查看衝突的主題，進而混淆模型。

Then I will go through and select only the three technical papers that contain the actual code logic.

然後我會逐一選取那三篇包含實際程式碼邏輯的技術論文。

Now effectively the other documents do not exist to the AI.

現在，對 AI 來說，其他文件實際上並不存在。

字幕列表影片播放

如何讓 NotebookLM 比 99% 的人更好用！ (How to Use Notebooklm Better than 99% of People)

perspective

specific

approach

content